[SPARK-2410][SQL] Merging Hive Thrift/JDBC server

(This is a replacement of #1399, trying to fix potential `HiveThriftServer2` port collision between parallel builds. Please refer to [these comments](#1399 (comment)) for details.)

JIRA issue: [SPARK-2410](https://issues.apache.org/jira/browse/SPARK-2410)

Merging the Hive Thrift/JDBC server from [branch-1.0-jdbc](https://github.com/apache/spark/tree/branch-1.0-jdbc).

Thanks chenghao-intel for his initial contribution of the Spark SQL CLI.

Author: Cheng Lian <[email protected]>

Closes #1600 from liancheng/jdbc and squashes the following commits:

ac4618b [Cheng Lian] Uses random port for HiveThriftServer2 to avoid collision with parallel builds
090beea [Cheng Lian] Revert changes related to SPARK-2678, decided to move them to another PR
21c6cf4 [Cheng Lian] Updated Spark SQL programming guide docs
fe0af31 [Cheng Lian] Reordered spark-submit options in spark-shell[.cmd]
199e3fb [Cheng Lian] Disabled MIMA for hive-thriftserver
1083e9d [Cheng Lian] Fixed failed test suites
7db82a1 [Cheng Lian] Fixed spark-submit application options handling logic
9cc0f06 [Cheng Lian] Starts beeline with spark-submit
cfcf461 [Cheng Lian] Updated documents and build scripts for the newly added hive-thriftserver profile
061880f [Cheng Lian] Addressed all comments by @pwendell
7755062 [Cheng Lian] Adapts test suites to spark-submit settings
40bafef [Cheng Lian] Fixed more license header issues
e214aab [Cheng Lian] Added missing license headers
b8905ba [Cheng Lian] Fixed minor issues in spark-sql and start-thriftserver.sh
f975d22 [Cheng Lian] Updated docs for Hive compatibility and Shark migration guide draft
3ad4e75 [Cheng Lian] Starts spark-sql shell with spark-submit
a5310d1 [Cheng Lian] Make HiveThriftServer2 play well with spark-submit
61f39f4 [Cheng Lian] Starts Hive Thrift server via spark-submit
2c4c539 [Cheng Lian] Cherry picked the Hive Thrift server

Author: liancheng

.gitignore

@@ -57,3 +57,4 @@ metastore_db/
 metastore/
 warehouse/
 TempStatsStore/
+sql/hive-thriftserver/test_warehouses

assembly/pom.xml

@@ -165,6 +165,16 @@
         </dependency>
       </dependencies>
     </profile>
+    <profile>
+      <id>hive-thriftserver</id>
+      <dependencies>
+        <dependency>
+          <groupId>org.apache.spark</groupId>
+          <artifactId>spark-hive-thriftserver_${scala.binary.version}</artifactId>
+          <version>${project.version}</version>
+        </dependency>
+      </dependencies>
+    </profile>
     <profile>
       <id>spark-ganglia-lgpl</id>
       <dependencies>

bagel/pom.xml

@@ -28,7 +28,7 @@
   <groupId>org.apache.spark</groupId>
   <artifactId>spark-bagel_2.10</artifactId>
   <properties>
-     <sbt.project.name>bagel</sbt.project.name>
+    <sbt.project.name>bagel</sbt.project.name>
   </properties>
   <packaging>jar</packaging>
   <name>Spark Project Bagel</name>

bin/beeline

@@ -0,0 +1,45 @@
+#!/usr/bin/env bash
+
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+# Figure out where Spark is installed
+FWDIR="$(cd `dirname $0`/..; pwd)"
+
+# Find the java binary
+if [ -n "${JAVA_HOME}" ]; then
+  RUNNER="${JAVA_HOME}/bin/java"
+else
+  if [ `command -v java` ]; then
+    RUNNER="java"
+  else
+    echo "JAVA_HOME is not set" >&2
+    exit 1
+  fi
+fi
+
+# Compute classpath using external script
+classpath_output=$($FWDIR/bin/compute-classpath.sh)
+if [[ "$?" != "0" ]]; then
+  echo "$classpath_output"
+  exit 1
+else
+  CLASSPATH=$classpath_output
+fi
+
+CLASS="org.apache.hive.beeline.BeeLine"
+exec "$RUNNER" -cp "$CLASSPATH" $CLASS "$@"

bin/compute-classpath.sh

@@ -52,6 +52,7 @@ if [ -n "$SPARK_PREPEND_CLASSES" ]; then
   CLASSPATH="$CLASSPATH:$FWDIR/sql/catalyst/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/sql/core/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/sql/hive/target/scala-$SCALA_VERSION/classes"
+  CLASSPATH="$CLASSPATH:$FWDIR/sql/hive-thriftserver/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/yarn/stable/target/scala-$SCALA_VERSION/classes"
 fi
 

bin/spark-shell

@@ -46,11 +46,11 @@ function main(){
         # (see https://github.com/sbt/sbt/issues/562).
         stty -icanon min 1 -echo > /dev/null 2>&1
         export SPARK_SUBMIT_OPTS="$SPARK_SUBMIT_OPTS -Djline.terminal=unix"
-        $FWDIR/bin/spark-submit spark-shell "$@" --class org.apache.spark.repl.Main
+        $FWDIR/bin/spark-submit --class org.apache.spark.repl.Main spark-shell "$@"
         stty icanon echo > /dev/null 2>&1
     else
         export SPARK_SUBMIT_OPTS
-        $FWDIR/bin/spark-submit spark-shell "$@" --class org.apache.spark.repl.Main
+        $FWDIR/bin/spark-submit --class org.apache.spark.repl.Main spark-shell "$@"
     fi
 }
 

bin/spark-shell.cmd

@@ -19,4 +19,4 @@ rem
 
 set SPARK_HOME=%~dp0..
 
-cmd /V /E /C %SPARK_HOME%\bin\spark-submit.cmd spark-shell %* --class org.apache.spark.repl.Main
+cmd /V /E /C %SPARK_HOME%\bin\spark-submit.cmd spark-shell --class org.apache.spark.repl.Main %*

bin/spark-sql

@@ -0,0 +1,36 @@
+#!/usr/bin/env bash
+
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+#
+# Shell script for starting the Spark SQL CLI
+
+# Enter posix mode for bash
+set -o posix
+
+# Figure out where Spark is installed
+FWDIR="$(cd `dirname $0`/..; pwd)"
+
+if [[ "$@" = *--help ]] || [[ "$@" = *-h ]]; then
+  echo "Usage: ./sbin/spark-sql [options]"
+  $FWDIR/bin/spark-submit --help 2>&1 | grep -v Usage 1>&2
+  exit 0
+fi
+
+CLASS="org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver"
+exec "$FWDIR"/bin/spark-submit --class $CLASS spark-internal $@

core/pom.xml

@@ -28,7 +28,7 @@
   <groupId>org.apache.spark</groupId>
   <artifactId>spark-core_2.10</artifactId>
   <properties>
-     <sbt.project.name>core</sbt.project.name>
+    <sbt.project.name>core</sbt.project.name>
   </properties>
   <packaging>jar</packaging>
   <name>Spark Project Core</name>

core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala

@@ -46,6 +46,10 @@ object SparkSubmit {
   private val CLUSTER = 2
   private val ALL_DEPLOY_MODES = CLIENT | CLUSTER
 
+  // A special jar name that indicates the class being run is inside of Spark itself, and therefore
+  // no user jar is needed.
+  private val SPARK_INTERNAL = "spark-internal"
+
   // Special primary resource names that represent shells rather than application jars.
   private val SPARK_SHELL = "spark-shell"
   private val PYSPARK_SHELL = "pyspark-shell"
@@ -257,7 +261,9 @@ object SparkSubmit {
     // In yarn-cluster mode, use yarn.Client as a wrapper around the user class
     if (clusterManager == YARN && deployMode == CLUSTER) {
       childMainClass = "org.apache.spark.deploy.yarn.Client"
-      childArgs += ("--jar", args.primaryResource)
+      if (args.primaryResource != SPARK_INTERNAL) {
+        childArgs += ("--jar", args.primaryResource)
+      }
       childArgs += ("--class", args.mainClass)
       if (args.childArgs != null) {
         args.childArgs.foreach { arg => childArgs += ("--arg", arg) }
@@ -332,7 +338,7 @@ object SparkSubmit {
    * Return whether the given primary resource represents a user jar.
    */
   private def isUserJar(primaryResource: String): Boolean = {
-    !isShell(primaryResource) && !isPython(primaryResource)
+    !isShell(primaryResource) && !isPython(primaryResource) && !isInternal(primaryResource)
   }
 
   /**
@@ -349,6 +355,10 @@ object SparkSubmit {
     primaryResource.endsWith(".py") || primaryResource == PYSPARK_SHELL
   }
 
+  private[spark] def isInternal(primaryResource: String): Boolean = {
+    primaryResource == SPARK_INTERNAL
+  }
+
   /**
    * Merge a sequence of comma-separated file lists, some of which may be null to indicate
    * no files, into a single comma-separated string.